本研究於個人數位註釋應用程式iPARIS上，建立影像標籤註釋之功能，稱為iPARIS-PLUS。它提供不同於以往文字註釋的新方法，讓使用者可以有另一種選擇，也同時解決在面臨多國語系時的註釋問題，並有效的降低記錄所花費之時間。iPARIS-Plus能讓使用者保有在行動裝置上紀實之便利性的同時，也能兼顧記錄的完整性，讓人們不再將記錄視為一種麻煩。除此之外，我們透過群眾外包的力量將用於註釋的影像標籤轉換為文字後儲存於資料庫中，解決原先因多國語系註釋問題讓使用者無法輸入文字，導致資料庫缺少該筆資料而造成資料空缺。在評估方面，受測者認為影像標籤註釋之方法可以有效的解決多國語系註釋之問題，以及有效節省在行動裝置上打字之時間，更加強了記錄的便利性與完整性，同時也帶來不同以往的新鮮感。而我們藉由群眾外包得到良好的解析率，並且從歷程記錄中發現群眾外包於運作上，越多專業之群眾並不一定帶來越好的成果，只仰賴少部分專業之群眾提供貢獻，反而能減少問題產生，進而得到較好之結果。 / In this study, we created the function of image tags annotating in the application, iPARIS-Plus. It provided a new method of annotation which is different from the text annotations, therefore, users could have another choice. This function could solve the problem of multilingual annotation and reduce the time effectively when users take for the record. iPARIS-Plus allows users to retain the convenience of recording on their mobile device, at the same time, it also considers the integrity of the records, so let people will no longer feel recording is a trouble. In addition, we converted the image tags that used to annotate into text through the crowdsourcing system to solve the problem which users couldn’t enter text because of the multilingual annotation, it resulted in a lack of databases. In the evaluation, users argued that the image tags annotation method could solve the problem of multilingual annotation effectively, as well as saving the time they typing on their moblie devices, even more it can enhance the integrity and convenience of records. We got a good resolution rate of converting the image tags into text by crowdsourcing system and found that more professional crowds do not bring better results. On the contrary, we could rely on a few of professional crowds to reduce the problems, then got a better results.

除了文字訊息，張貼相片也是臉書使用者常用的功能，這些上傳的照片種類繁多，可能是自拍照、風景照、或食物照等等，本論文的研究以影像分析為出發點，探討相片內容跟發佈者間之關係，希望藉由相片獲得的資訊，輔助分析使用者樣貌。 本研究共收集32位受測者上傳至臉書的相片，利用電腦視覺技術分析圖像內容，如人臉偵測、環境識別、找出影像上視覺顯著的區域等，藉由這些工具所提供的資訊，將照片加註標籤，以及進行自動分類，並以此兩個層次的資訊做為特徵向量，利用階層式演算法進行使用者分群，再根據實驗結果去分析每一群的行為特性。 透過此研究，可對使用者進行初步分類、瞭解不同的使用者樣貌，並嘗試回應相關問題，如使用者所張貼之相片種類統計、不同性別使用者的上傳行為、 依據上傳圖像內容，進行使用者樣貌分類等，深化我們對於臉書相片上傳行為的理解。 / Apart from text messages, photo posting is a popular function of Facebook. The uploaded photos are of various nature, including selfie, outdoor scenes, and food. In this thesis, we employ state-of-the-art computer vision techniques to analyze image content and establish the relationship between user profile and the type of photos posted. We collected photos from 32 Facebook users. We then applied techniques such as face detection, scene understanding and saliency map identification to gather information for automatic image tagging and classification. Grouping of users can be achieved either by tag statistics or photo classes. Characteristics of each group can be further investigated based on the results of hierarchical clustering. We wish to identify profiles of different users and respond to questions such as the type of photos most frequently posted, gender differentiation in photo posting behavior and user classification according to image content, which will promote our understanding of photo uploading activities on Facebook.

生活於數位時代，巨量的個人生命記憶使得人們難以輕易解讀，必須經過檢索或標籤化才可以進一步瞭解背後的意涵。本研究著力個人記憶裡繁瑣及週期性的廣泛事件，進行於「情節記憶語意化」以及「何以權衡大眾與個人資訊」兩議題之探討。透過生命記憶平台裡影像標籤自動化功能，我們以時空資訊為索引提出持續性概念重構模型，整合共同知識、個人近況以及個人偏好三項因素，模擬人們對每張照片下標籤時的認知歷程，改善其廣泛事件上註釋困難。在實驗設計上，實作大眾資訊模型、個人資訊模型以及本研究持續性概念重構模型，並招收九位受試者來剖析其認知歷程以及註釋效率。實驗結果顯示持續性概念重構模型解決了上述大眾與個人兩模型上的極限，即舊地重遊、季節性活動、非延續性活動性質以及資訊邊界註釋上的問題，因此本研究達成其個人生命記憶在廣泛事件之語意標籤自動化示範。 / In the digital era, labeling and retrieving are ways to understand the meaning behind a huge amount of lifetime archive. Foucusing on tedious and periodic general events, this study will discuss two issues: (1) the semantics of episodic memory (2) the trade-off between common and personal knowledge. Using the automatic image-tagging technique of lifelong digital archiving system, we propose the Coutinuous Reconceptualization Model which models the cognitive processing of examplar categorization based on temporal-spatial information. Integrating the common knowlegde, current personal life and hobby, the Continuous Reconceptualization Model improves the tagging efficiency. In this experiment, we compare the accuracy of cognitive modeling and tagging efficiency of the three distinct models: the common knowledge model, personal knowledge model and Coutinuous Reconceptualization Model. Nine participants were recruited to label the photos. The results show that the Continous Reconceptualization Model overcomes the limitations inherent in other models, including the auto-tagging problems of modeling certain situations, such as re-visiting places, seasonal activities, noncontinuous activities and information boundary. Consequently, the Continuous Reconceptualization Model demonstrated the efficiency of the automatic image-tagging technique used in the semantic labeling of the general event of personal memory.